Etudiant : ZANBOUAA ASMAE

Filière : Master Web Intelligence et Sciences des Données (WISD)

Encadrant : Pr. RIFFI JAMAL

Annèe : 2022

Résumé : A survey of the literature in the field of medical image segmentation using deep convolutional neural networks is presented in this work, as well as the various metrics for evaluating segmentation tasks and the challenges with these networks. This work describes how deep learning can be used to segment tumors from MRI scans, as well as describing, examining and comparing various deep learning architectures used in medical image segmentation. The most commonly medical image datasets in 2D and 3D formats (LGG Segmentation Dataset 2D / BraTS2020 3D ) were used for training and evaluation.